EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated lesion detection in cotton leaf visuals using deep learning

Frnaz Akbar, Yassine Aribi, Syed Muhammad Usman, Hamzah Faraj, Ahmed Murayr, Fawaz Alasmari, Shehzad Khalid

PeerJ Computer Science · 18.10.2024 · 10 · e2369

DOI: 10.7717/peerj-cs.2369 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 18.10.2024. Verfasst von Frnaz Akbar und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Creative Technologies, Faculty of Computing and AI, Air University, Islamabad, Pakistan. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Deanship of Graduate Studies and Scientific Research, Taif University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cotton is one of the major cash crop in the agriculture led economies across the world. Cotton leaf diseases affects its yield globally. Determining cotton lesions on leaves is difficult when the area is big and the size of lesions is varied. Automated cotton lesion detection is quite useful; however, it is challenging due to fewer disease class, limited size datasets, class imbalance problems, and need of comprehensive evaluation metrics. We propose a novel deep learning based method that augments the data using generative adversarial networks (GANs) to reduce the class imbalance issue and an ensemble-based method that combines the feature vector obtained from the three deep learning architectures including VGG16, Inception V3, and ResNet50. The proposed method offers a more precise, efficient and scalable method for automated detection of diseases of cotton crops. We have implemented the proposed method on publicly available dataset with seven disease and one health classes and have achieved highest accuracy of 95% and F-1 score of 98%. The proposed method performs better than existing state of the art methods.

Schlagwörter

Stichwörter der Autor:innen

CNNCotton disease detectionDeep learningFeature fusionPrecision agriculture

Autor:innen und Institutionen

  • Department of Creative Technologies, Faculty of Computing and AI, Air University, Islamabad, Pakistan.
  • Department of Science and Technology, College of Ranyah, Taif University, Taif, Saudi Arabia.
  • Department of Computer Science, Bahria School of Engineering and Applied Sciences, Islamabad, Pakistan.
  • Department of Computer Engineering, Bahria School of Engineering and Applied Sciences, Islamabad, Pakistan.

Förderung

  • The Deanship of Graduate Studies and Scientific Research, Taif University

Zitieren

APA

Akbar, F., Aribi, Y., Muhammad Usman, S., Faraj, H., Murayr, A., Alasmari, F., & Khalid, S. (2024). Automated lesion detection in cotton leaf visuals using deep learning. PeerJ Computer Science, 10, e2369. https://doi.org/10.7717/peerj-cs.2369

Vancouver

Akbar F, Aribi Y, Muhammad Usman S, Faraj H, Murayr A, Alasmari F, et al. Automated lesion detection in cotton leaf visuals using deep learning. PeerJ Computer Science. 2024;10:e2369. doi:10.7717/peerj-cs.2369

BibTeX
@article{Akbar2024,
  author = {Akbar, Frnaz and Aribi, Yassine and Muhammad Usman, Syed and Faraj, Hamzah and Murayr, Ahmed and Alasmari, Fawaz and Khalid, Shehzad},
  title = {Automated lesion detection in cotton leaf visuals using deep learning},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e2369},
  doi = {10.7717/peerj-cs.2369}
}
Kostenlos starten →